Improvement of Apriori algorithm based on matrix compression

摘要

The traditional association rule mining algorithm for Apriori time cost, the lack of Apriori algorithm, based on the theory of relational algebra, relation matrix and related operations by given search association rules from the frequent itemsets mining algorithm based on relation algebra theory. Using the relation matrix to scan the database only once, in order to reduce the running time of the algorithm, frequent itemsets mining, finally the simulation results comparing the two execution time of the algorithm, the effect of sample data and the minimum support degree on the performance of the algorithm is discussed. The simulation results show that the improved algorithm is efficient and reduces the running time of mining frequent itemsets.